Cence – UX Research Case Study

Overview

Cence is an AI-driven fintech platform designed to help users make smarter financial decisions by recommending the best payment method, credit card rewards, and personalised offers at the moment of purchase. It is primarily designed for residents living in the UAE.

The ecosystem consists of two primary products:

1. Consumer Mobile Application (Flutter) – A cross-platform iOS and Android app that provides intelligent financial decision surfaces.

2. Merchant Portal (NextJS) – A web platform that allows merchants to publish offers, track engagement, and optimise performance based on behavioural insights.

My role focused on UX research across both sides of the marketplace, ensuring that:

• Users receive timely and actionable financial guidance.

• Merchants can create offers that perform well and drive conversions.
  
  
  

  Platform Intelligence — Shared Section

  Cence Platform Intelligence

  Cence is more than two separate products — it is a behavioural intelligence ecosystem. Both the consumer app and the merchant portal connect to a central AI-driven intelligence layer that interprets behaviour and guides product decisions across the platform.

  This section explains how user behaviour, AI intelligence, and merchant insights work together to create value on both sides.

  Platform Intelligence Overview

  • Central Intelligence Layer: Collects and analyses user behaviour signals (location, spending patterns, payment choices).

  • Consumer App: Receives real-time recommendations and contextual guidance.

  • Merchant Portal: Receives behavioural insights to optimise offers and campaigns.

  • Two-Way Feedback Loop: Consumer actions inform merchant decisions; merchant campaigns influence consumer behaviour.

  Key Principles:

  1. Decision-Focused — Prioritise actionable guidance over dashboards.

  2. Contextual — Recommendations delivered at the moment of decision.

  3. Transparent AI — Build trust with explainable outputs for both users and merchants.

  4. Continuous Learning — Behavioural signals feed AI to optimise recommendations and campaigns in real time.

  

  Explanation:

  • User Behaviour Signals: Actions captured from app usage, card choices, and spending patterns.

  • Cence Intelligence Layer: Processes signals using behavioural algorithms and AI models.

  • Decision Interfaces: Deliver real-time recommendations in the consumer app.

  • Offer Personalisation: Tailor offers user habits, location, and reward optimisation.

  • Merchant Insights: Enable merchants to optimise campaigns using actionable behavioural data.

  

  Key Takeaways:

  • The platform is not two independent products — it is a single ecosystem with feedback loops.

  • Consumer behaviour drives merchant optimisation, and merchant campaigns influence user engagement.

  • Designing the central intelligence layer first allows both products to iterate quickly and consistently.